{"type":"ScholarlyArticle","title":"Enhancing Nighttime Semantic Segmentation with Visual-Linguistic Priors and Wavelet Transform","authors":[{"name":"Jianhou Zhou","slug":"jianhou-zhou","given":"Jianhou","family":"Zhou","affiliation":""},{"name":"Xiaolong Zhou","slug":"xiaolong-zhou","given":"Xiaolong","family":"Zhou","affiliation":""},{"name":"Sixian Chan","slug":"sixian-chan","given":"Sixian","family":"Chan","affiliation":""},{"name":"Zhaomin Chen","slug":"zhaomin-chen","given":"Zhaomin","family":"Chen","affiliation":""},{"name":"Xiaoqin Zhang","slug":"xiaoqin-zhang","given":"Xiaoqin","family":"Zhang","affiliation":""}],"abstract":"Nighttime semantic segmentation is a critical yet challenging task in autonomous driving. Most existing methods are designed for daytime scenarios, resulting in poor nighttime performance due to texture loss and decreased object visibility. Low-light enhancement was applied before segmentation but failed to recover nighttime-specific details, introducing noise or losing delicate structures. Recent work shows that large-scale image-text pairs can effectively leverage natural language priors to guide visual representation, achieving remarkable performance across various downstream visual tasks. However, effectively employing visual-linguistic priors for nighttime semantic segmentation remains underexplored. To address these issues, we propose Text-WaveletFormer, a novel end-to-end framework that integrates text prompts and wavelet-based texture enhancement. Specifically, to compensate for the low recognizability of objects in nighttime scenes, we design a Text-Image Fusion Module (TIFM) to incorporate textual priors to improve nighttime object recognition. In addition, to alleviate the lack of texture details in nighttime conditions, we introduce a Wavelet Guided Texture Amplifier Module (WTAM) to fuse wavelet and raw image features via cross-attention, restoring low-light details. Finally, extensive experiments on benchmarks including NightCity, NightCity-fine, BDD100K, and CityScapes demonstrate our method’s superior performance over existing approaches.","doi":"10.24963/ijcai.2025/888","url":"https://ijcai.org/proceedings/2025/888","pdf":"https://ijcai.org/proceedings/2025/0888.pdf","markdown":"https://ijcai.org/proceedings/2025/888.md","bibtex":"https://ijcai.org/proceedings/2025/bibtex/888","volume":{"slug":"2025","title":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2025","url":"https://ijcai.org/proceedings/2025/","year":2025,"location":"Montreal, Canada","dates":"16-22 August 2025","editors":"James Kwok","isbn":"978-1-956792-06-5","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2025"},"section":"Multidisciplinary Topics and Applications","track":"Main Track","number":888,"pages":{"first":7985,"last":7993},"keywords":["Computer Vision: CV: Segmentation, grouping and shape analysis","Multidisciplinary Topics and Applications: MTA: Computer games","Knowledge Representation and Reasoning: KRR: Learning and reasoning","Natural Language Processing: NLP: Information extraction"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}